Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751403Ab0LQFVv (ORCPT ); Fri, 17 Dec 2010 00:21:51 -0500 Received: from rcsinet10.oracle.com ([148.87.113.121]:18430 "EHLO rcsinet10.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751177Ab0LQFVu convert rfc822-to-8bit (ORCPT ); Fri, 17 Dec 2010 00:21:50 -0500 MIME-Version: 1.0 Message-ID: Date: Thu, 16 Dec 2010 21:15:07 -0800 (PST) From: Dan Magenheimer To: Chris Mason , akpm@linux-foundation.org, matthew@wil.cx, linux-kernel@vger.kernel.org, linux-mm@kvack.org, ngupta@vflare.org, jeremy@goop.org, Kurt Hackel , npiggin@kernel.dk, riel@redhat.com, Konrad Wilk , mel@csn.ul.ie, minchan.kim@gmail.com Subject: RE: [PATCH V0 1/4] kztmem: simplified radix tree data structure support References: <20101207180653.GA28115@ca-server1.us.oracle.com dd88185d-bc2c-4d65-8730-8b1fc712306a@default> In-Reply-To: X-Priority: 3 X-Mailer: Oracle Beehive Extensions for Outlook 2.0.1.4.1.0 (410211) [OL 12.0.6539.5000] Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2013 Lines: 49 > A monolithic patch containing all of kztmem, cleancache, and frontswap > that applies cleanly to 2.6.36 can be found at: > > http://oss.oracle.com/projects/tmem/dist/files/kztmem/kztmem-linux- > 2.6.36-101207.patch > > (Or http://oss.oracle.com/projects/tmem and Downloads and kztmem > patches) > > I'm a git novice but can prepare a git tree also if desired. > > To try kztmem: > > 1) apply the monolithic patch to 2.6.36 > 2) rebuild your config ensuring that CONFIG_KZTMEM, CONFIG_CLEANCACHE, > CONFIG_FRONTSWAP, and CONFIG_ZRAM (for xvMalloc) become enabled > 3) rebuild and reboot with "kztmem" as a kernel boot parameter > 4) see /sys/kernel/mm/kztmem/* for statistics... note that with > lots of RAM and no swapping, little or no activity will be seen > > As I said, there are known weird bugs that may or may not show > up in your configuration and build environment, so be prepared > in advance that the kernel may crash... removing kztmem as > a boot parameter should disable kztmem and result in a normal boot. > > Thanks in advance for trying and testing (and, if you are so > inclined, debugging) kztmem! I'll be happy to answer any > questions on- or off-list! FYI, in case anyone was thinking about giving it a spin, I have just posted an update of the (monolithic) kztmem patch here: http://oss.oracle.com/projects/tmem/dist/files/kztmem/kztmem-linux-2.6.36-101207.patch I think all the weird bugs and crashes are now gone, though I have some concurrency rework to do after some feedback from Jeremy Fitzhardinge, and that's not going to happen until after the holidays. So I am posting this intermediate version if you want to try it, but please hold off on any detailed code review until I post v1 to lkml/linux-mm. Thanks, Dan -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/